1
|
Liu C, Yang WY, Cheng F, Chien CW, Chuang YC, Jin Y. Identification of key risk factors for venous thromboembolism in urological inpatients based on the Caprini scale and interpretable machine learning methods. Thromb J 2024; 22:76. [PMID: 39152448 PMCID: PMC11328390 DOI: 10.1186/s12959-024-00645-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Accepted: 08/07/2024] [Indexed: 08/19/2024] Open
Abstract
PURPOSE To identify the key risk factors for venous thromboembolism (VTE) in urological inpatients based on the Caprini scale using an interpretable machine learning method. METHODS VTE risk data of urological inpatients were obtained based on the Caprini scale in the case hospital. Based on the data, the Boruta method was used to further select the key variables from the 37 variables in the Caprini scale. Furthermore, decision rules corresponding to each risk level were generated using the rough set (RS) method. Finally, random forest (RF), support vector machine (SVM), and backpropagation artificial neural network (BPANN) were used to verify the data accuracy and were compared with the RS method. RESULTS Following the screening, the key risk factors for VTE in urology were "(C1) Age," "(C2) Minor Surgery planned," "(C3) Obesity (BMI > 25)," "(C8) Varicose veins," "(C9) Sepsis (< 1 month)," (C10) "Serious lung disease incl. pneumonia (< 1month) " (C11) COPD," "(C16) Other risk," "(C18) Major surgery (> 45 min)," "(C19) Laparoscopic surgery (> 45 min)," "(C20) Patient confined to bed (> 72 h)," "(C18) Malignancy (present or previous)," "(C23) Central venous access," "(C31) History of DVT/PE," "(C32) Other congenital or acquired thrombophilia," and "(C34) Stroke (< 1 month." According to the decision rules of different risk levels obtained using the RS method, "(C1) Age," "(C18) Major surgery (> 45 minutes)," and "(C21) Malignancy (present or previous)" were the main factors influencing mid- and high-risk levels, and some suggestions on VTE prevention were indicated based on these three factors. The average accuracies of the RS, RF, SVM, and BPANN models were 79.5%, 87.9%, 92.6%, and 97.2%, respectively. In addition, BPANN had the highest accuracy, recall, F1-score, and precision. CONCLUSIONS The RS model achieved poorer accuracy than the other three common machine learning models. However, the RS model provides strong interpretability and allows for the identification of high-risk factors and decision rules influencing high-risk assessments of VTE in urology. This transparency is very important for clinicians in the risk assessment process.
Collapse
Affiliation(s)
- Chao Liu
- Medical Department, The Second Affiliated Hospital of Hebei North University, Zhangjiakou, 075000, Hebei, China
- Institute for Hospital Management, Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, Guangdong, China
| | - Wei-Ying Yang
- Nursing Department, Taizhou Hospital of Zhejiang Province Affiliated to Wenzhou Medical University, Linhai, 317000, Zhejiang, China
| | - Fengmin Cheng
- Nursing Department, Taizhou Hospital of Zhejiang Province Affiliated to Wenzhou Medical University, Linhai, 317000, Zhejiang, China
| | - Ching-Wen Chien
- Institute for Hospital Management, Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, Guangdong, China.
| | - Yen-Ching Chuang
- Business College, Taizhou University, Taizhou, 318000, Zhejiang, China.
- Institute of Public Health & Emergency Management, Taizhou University, Taizhou, 318000, Zhejiang, China.
- Key Laboratory of evidence-based Radiology of Taizhou, Linhai, 317000, Zhejiang, China.
| | - Yanjun Jin
- Department of Urology, Taizhou Hospital of Zhejiang Province Affiliated to Wenzhou Medical University, Linhai, 317000, Zhejiang, China.
| |
Collapse
|
2
|
Diers J, Baumann N, Baum P, Uttinger KL, Wagner JC, Kranke P, Meybohm P, Germer CT, Wiegering A. Availability in ECMO Reduces the Failure to Rescue in Patients With Pulmonary Embolism After Major Surgery: A Nationwide Analysis of 2.4 Million Cases. ANNALS OF SURGERY OPEN 2024; 5:e416. [PMID: 38911642 PMCID: PMC11192012 DOI: 10.1097/as9.0000000000000416] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Accepted: 03/11/2024] [Indexed: 06/25/2024] Open
Abstract
Objective Postoperative pulmonary embolism (PE) is a rare but potentially life-threatening complication, which can be treated with extracorporeal membrane oxygenation (ECMO) therapy, a novel therapy option for acute cardiorespiratory failure. We postulate that hospitals with ECMO availability have more experienced staff, technical capabilities, and expertise in treating cardiorespiratory failure. Design A retrospective analysis of surgical procedures in Germany between 2012 and 2019 was performed using hospital billing data. High-risk surgical procedures for postoperative PE were analyzed according to the availability of and expertise in ECMO therapy and its effect on outcome, regardless of whether ECMO was used in patients with PE. Methods Descriptive, univariate, and multivariate analyses were applied to identify possible associations and correct for confounding factors (complications, complication management, and mortality). Results A total of 13,976,606 surgical procedures were analyzed, of which 2,407,805 were defined as high-risk surgeries. The overall failure to rescue (FtR) rate was 24.4% and increased significantly with patient age, as well as type of surgery. The availability of and experience in ECMO therapy (defined as at least 20 ECMO applications per year; ECMO centers) are associated with a significantly reduced FtR in patients with PE after high-risk surgical procedures. In a multivariate analysis, the odds ratio (OR) for FtR after postoperative PE was significantly lower in ECMO centers (OR, 0.75 [0.70-0.81], P < 0.001). Conclusions The availability of and expertise in ECMO therapy lead to a significantly reduced FtR rate of postoperative PE. This improved outcome is independent of the use of ECMO in these patients.
Collapse
Affiliation(s)
- Johannes Diers
- From the Department of General, Visceral, Transplant, Vascular, and Pediatric Surgery, University Hospital Würzburg, Würzburg, Germany
| | - Nikolas Baumann
- From the Department of General, Visceral, Transplant, Vascular, and Pediatric Surgery, University Hospital Würzburg, Würzburg, Germany
| | - Philip Baum
- Department of Thoracic Surgery, Thoraxklinik at Heidelberg University Hospital, Heidelberg, Germany
| | - Konstantin L. Uttinger
- From the Department of General, Visceral, Transplant, Vascular, and Pediatric Surgery, University Hospital Würzburg, Würzburg, Germany
- Department of Visceral, Transplant, Thoracic, and Vascular Surgery, Leipzig University Hospital, Leipzig, Germany
| | - Johanna C. Wagner
- From the Department of General, Visceral, Transplant, Vascular, and Pediatric Surgery, University Hospital Würzburg, Würzburg, Germany
| | - Peter Kranke
- Department of Anaesthesiology, Intensive Care, Emergency, and Pain Medicine, University Hospital Würzburg, Würzburg, Germany
| | - Patrick Meybohm
- Department of Anaesthesiology, Intensive Care, Emergency, and Pain Medicine, University Hospital Würzburg, Würzburg, Germany
| | - Christoph-Thomas Germer
- From the Department of General, Visceral, Transplant, Vascular, and Pediatric Surgery, University Hospital Würzburg, Würzburg, Germany
- Comprehensive Cancer Centre Mainfranken, University Hospital Würzburg, Würzburg, Germany
| | - Armin Wiegering
- From the Department of General, Visceral, Transplant, Vascular, and Pediatric Surgery, University Hospital Würzburg, Würzburg, Germany
- Comprehensive Cancer Centre Mainfranken, University Hospital Würzburg, Würzburg, Germany
- Department of Biochemistry and Molecular Biology, University of Würzburg, Würzburg, Germany
| |
Collapse
|
3
|
Søndergaard MMA, Nordsmark M, Nielsen KM, Valentin JB, Johnsen SP, Poulsen SH. High Incidence of Cardiovascular Disease in Patients With Oesophageal Cancer-A Registry-Based Cohort Study. Heart Lung Circ 2024; 33:664-674. [PMID: 38336543 DOI: 10.1016/j.hlc.2023.12.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 12/14/2023] [Accepted: 12/23/2023] [Indexed: 02/12/2024]
Abstract
BACKGROUND The cardiovascular disease (CVD) burden among patients with oesophageal cancer (EC) treated with curative intent is unclear. AIM To determine CVD incidence and all-cause mortality in patients with EC. METHOD Danish national health registries were used to identify patients diagnosed with primary EC between 2008 and 2018. Each EC patient was matched with 10 individuals from the general population. The primary endpoint was a CVD hospital contact (CVD-HC), either admission or outpatient contact. Cox proportional hazard regression models were used to compare the risk of incident CVD-HCs between the cohorts. RESULTS The study included 1,525 patients with EC and 15,250 individuals from the general population. Patients with EC had a post-diagnosis one-year adjusted hazard ratio (HR) of CVD-HC of 6.1 (95% confidence intervals [CIs] 5.6-6.8) compared with the general population. During the next nine years, the risk of CVD-HC was comparable between the two cohorts, with an adjusted HR of 1.0 (95% CI 0.9-1.3). Patients with EC, and particularly those with prevalent CVD, had a high risk of atrial fibrillation, ischaemic heart disease, and venous thromboembolism within the first year after EC diagnosis. Prevalent CVD among patients with EC was not associated with higher mortality. CONCLUSIONS CVD morbidity was transiently increased in the first year following EC diagnosis compared with the general population. All-cause mortality risks were high but did not appear to be affected by prevalent CVD. The very high risk of CVD in patients with primary EC to be treated with curative intent calls for healthcare initiatives to advance preventive and post-treatment strategies.
Collapse
Affiliation(s)
- Mette Marie A Søndergaard
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark; Department of Medicine, Regional Hospital Horsens, Horsens, Denmark.
| | | | - Kirsten M Nielsen
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
| | - Jan B Valentin
- Danish Center for Health Services Research, Department of Clinical Medicine, Aalborg University, Aalborg Ø, Denmark
| | - Søren P Johnsen
- Danish Center for Health Services Research, Department of Clinical Medicine, Aalborg University, Aalborg Ø, Denmark
| | - Steen H Poulsen
- Department of Cardiology, Aarhus University Hospital, Aarhus N, Denmark
| |
Collapse
|
4
|
Rocco R, Reisenauer J. The Prevention of Venous Thromboembolism After Esophago-Gastric Surgery: A Never-Ending Story. Ann Surg Oncol 2022; 29:10.1245/s10434-022-11572-7. [PMID: 35352261 PMCID: PMC9174304 DOI: 10.1245/s10434-022-11572-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2022] [Accepted: 02/24/2022] [Indexed: 12/05/2022]
Affiliation(s)
- Raffaele Rocco
- Division of Thoracic Surgery, Department of Surgery, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA
| | - Janani Reisenauer
- Division of Thoracic Surgery, Department of Surgery, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA.
| |
Collapse
|
5
|
Theochari CA, Theochari NA, Mylonas KS, Papaconstantinou D, Giannakodimos I, Spartalis E, Patelis N, Schizas D. Venous Thromboembolism Following Major Abdominal Surgery for Cancer: A Guide for the Surgical Intern. Curr Pharm Des 2022; 28:787-797. [PMID: 35176975 DOI: 10.2174/1381612828666220217140639] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2021] [Accepted: 12/29/2021] [Indexed: 11/22/2022]
Abstract
BACKGROUND Venous thromboembolism (VTE) is a term used to compositely describe deep vein thrombosis (DVT) and pulmonary embolism (PE). Overall, the incidence of VTE after major abdominal and pelvic surgery has been reported to be between 10% and 40%. OBJECTIVE To estimate the incidence of post-operative VTE in patients undergoing major abdominal surgery for cancer, to identify risk factors associated with VTE, and to assess available thromboprophylaxis tools. METHODS A Medline and Cochrane literature search from database inception until February 1st, 2021 was performed according to the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guidelines. RESULTS Thirty-one studies met our eligibility criteria and were included in the current review. In total, 435,492 patients were identified and the overall incidence of VTE was 2.19%( 95% CI: 1.82-2.38). Τhe following risk factors were associated with VTE: smoking, advanced age (>70 years), a history of diabetes mellitus, American Society of Anesthesiologists' (ASA) classification of Physical Health class III or IV, a history of cardiovascular or pulmonary disease, a history of DVT or PE, elevated plasma fibrinogen level, c-reactive protein (CRP) level, cancer stage III or IV, postoperative acute respiratory distress syndrome (ARDS), prolonged postoperative hospital stay, previous steroid use, history of Inflammatory Bowel Disease (IBD), heart failure and neoadjuvant and adjuvant chemotherapy. CONCLUSION VTE remains an important complication after major abdominal surgery for cancer and seems to increase mortality rates.
Collapse
Affiliation(s)
- Christina A Theochari
- Third Department of Internal Medicine, National and Kapodistrian University of Athens, Thoracic Diseases General Hospital Sotiria, Athens, Greece
| | - Nikoletta A Theochari
- Department of Otorhinolaryngology, Head and Neck Surgery, General Hospital of Nikaia-Piraeus, Athens, Greece
| | - Konstantinos S Mylonas
- First Department of Surgery, National and Kapodistrian University of Athens, Laikon General Hospital, Athens, Greece
| | - Dimitrios Papaconstantinou
- Third Department of Surgery, National and Kapodistrian University of Athens, Attikon University Hospital, Athens, Greece
| | - Ilias Giannakodimos
- First Department of Surgery, National and Kapodistrian University of Athens, Laikon General Hospital, Athens, Greece
| | - Eleftherios Spartalis
- Department of Anatomy, School of Medicine, National and Kapodistrian University of Athens, Athens, Greece
| | - Nikolaos Patelis
- First Department of Surgery, National and Kapodistrian University of Athens, Laikon General Hospital, Athens, Greece
| | - Dimitrios Schizas
- First Department of Surgery, National and Kapodistrian University of Athens, Laikon General Hospital, Athens, Greece
| |
Collapse
|